Technical Workshop Series -Explaining Machine Learning Models with LIME in Python (2nd Offering) by: Nasrin Tavakoli

Wednesday, August 7, 2024 - 12:00

Technical Workshop Series

 

The School of Computer Science Presents…

 

Explaining Machine Learning Models with LIME in Python (2nd Offering)

 

Presenter:  Nasrin Tavakoli

Date: Wednesday, August 7th, 2024

Time:  12:00 PM

Location: 4th Floor at 300 Ouellette Avenue (School of Computer Science Advanced Computing Hub)

This is a hands-on workshop, please bring your laptop

 

Abstract: 

This workshop offers a practical introduction to Explainable AI (XAI), focusing on the use of LIME (Local Interpretable Model-agnostic Explanations). Designed for both beginners and those with some machine learning experience, it covers the essentials of model interpretability with hands-on practice. Participants will learn to set up a Python environment and will be guided through loading and preparing the Iris dataset with Pandas, training a Decision Tree classifier using Scikit-learn, and applying LIME to explain model predictions. The workshop emphasizes generating and visualizing explanations, demystifying the decision-making process of machine learning models. By the end of the session, attendees will understand how to enhance the transparency and trustworthiness of their models, equipped with both practical skills and a foundational understanding of XAI principles.

 

Workshop Outline:

· Introduction to XAI and LIME

· Setting Up Python Environment

· Preparing the Iris Dataset

· Training a Decision Tree Model

· Explaining Predictions with LIME

· Q&A and Wrap-Up

 

Prerequisites:

Participants should have a basic understanding of Python programming and a general familiarity with machine learning concepts. Don’t worry if you're new to Pandas or Scikit-learn – we'll guide you through everything you need to know!

 
Biography:

Nasrin Tavakoli is a Ph.D. student of Computer Science at the University of Windsor. Her field of study has been Artificial Intelligence and Machine Learning. During her master's program, she worked on breast cancer diagnosis based on deep features. She is continuing her research in Artificial Intelligence, specifically on Explainable AI, in the Ph.D. program.  

 

MAC STUDENTS ONLY - Register Here